Mine water disaster is closely related to the geological structure of the mine. A scientific evaluation of the complexity of the minefield structure can greatly contribute to mining safety. In this study, we optimized...
详细信息
Mine water disaster is closely related to the geological structure of the mine. A scientific evaluation of the complexity of the minefield structure can greatly contribute to mining safety. In this study, we optimized the fault impact index in the study area and proposed an improved locallinearembedding (LLE) algorithm by investigating the Shengquan coal mine. We analyzed the fault formation age and connectivity between faults in the study area, combined with topology theory, and based on previous studies. The mechanical properties of faults and the influence of small faults on the strata can be combined to derive a quantitative evaluation model of the structural complexity of mines. Based on the evaluation model, the study area was divided into a simple structural area, a medium structural area, and a complex structural area. By comparing the location of water inrush points in recent years with the three-dimensional high-density electrical exploration of the 21,304 working face, the effectiveness and rationality of structural complexity zoning were determined.
A new approach for identifying moving loads is proposed in which one can identify continuous or discontinuous loads from the response data by using a local linear embedding algorithm. This approach is especially well ...
详细信息
A new approach for identifying moving loads is proposed in which one can identify continuous or discontinuous loads from the response data by using a local linear embedding algorithm. This approach is especially well suited for moving loads that are difficult to measure directly and it does not depend on modeling the structures. Four simulated examples are conducted on a 5-m beam with four types of moving loads and the results verify the usefulness of our approach, but there is a small amount of distortion at some stages. The robustness of the approach is further verified by contaminating the response data with white noise of different levels, and the results show that the approach mentioned in this paper has good robustness. This identification approach for moving loads can be applied to aerospace engineering applications.
In order to solve the problem of high dimension in text classification, this paper imported local linear embedding algorithm for dimension reduction. However, the original LLE did not necessarily make the loss of info...
详细信息
ISBN:
(纸本)9780769538747
In order to solve the problem of high dimension in text classification, this paper imported local linear embedding algorithm for dimension reduction. However, the original LLE did not necessarily make the loss of information minimize in process of reduction, so we combinated its two loss function together and improved it firstly. Then, linked the improved LLE and supervised learning and support vector machine algorithm together, so this paper proposed a supervised locallinearembedding based SVM text classification algorithm. Finally, we designed three experiments for comparing, and the results of experiments indicated the algorithm could be used for dimension reduction effectively, and it did really improve the accurate rate in text classification
Device-free indoor human trajectory tracking is critical to support health care applications for elderly people. Many device-free localization algorithms depend on expensive hardware to achieve tracking accuracy. In c...
详细信息
Device-free indoor human trajectory tracking is critical to support health care applications for elderly people. Many device-free localization algorithms depend on expensive hardware to achieve tracking accuracy. In contrast to such algorithms, this paper proposes a new device-free human trajectory tracking algorithm for indoor environments based on channel state information that is extracted from a Wi-Fi network interface card, which is a low-cost component. The proposed algorithm first uses the characteristics of locally linearembedding to detect whether a person is moving and applies quadratic discriminant analysis to determine the new location of the person. The determined locations of the person are connected to form a trajectory. Experimental results revealed that the proposed algorithm provides an effective solution for passive human trajectory tracking.
Aiming at the problems of low detection efficiency and poor clustering effect in traditional abnormal network data mining process, an abnormal data mining model based on kernel extreme learning machine and particle sw...
详细信息
Aiming at the problems of low detection efficiency and poor clustering effect in traditional abnormal network data mining process, an abnormal data mining model based on kernel extreme learning machine and particle swarm optimisation is proposed. The enhanced local linear embedding algorithm is used to extract the features of abnormal network data, and the required feature dimensions are extracted repeatedly to obtain the corresponding features of target network data. K-means algorithm is introduced to cluster the target network data to increase the identification of data mining. By improving the particle swarm optimisation algorithm to optimise the parameters of the kernel limit learning machine, the final abnormal data mining results are the best. The experimental results show that the proposed method has high detection efficiency and good clustering effect, which fully proves the superiority of the proposed method and lays a foundation for the progress of abnormal network data mining technology.
Natural gas pipeline leakage is a common safety hazard, which can have a great impact on the economy and the environment. This paper proposed a novel manifold learning-enabled feature extraction method for natural gas...
详细信息
Natural gas pipeline leakage is a common safety hazard, which can have a great impact on the economy and the environment. This paper proposed a novel manifold learning-enabled feature extraction method for natural gas pipeline leakage diagnosis. Firstly, the natural gas pipeline working condition signal is decomposed and denoised by Variational mode decomposition (VMD). Secondly, the denoised pipeline signals were constructed into a form expressed by the Symmetric positive definite matrix (SPD) using the VMD reconstruction technique, and the geodesic distance measurement method was applied to the SPD matrix to make the data located on the SPD manifold. Then feature extraction is carried out by locallinearembedding (LLE) method based on asymmetric distance. Finally, pattern recognition of the features extracted in this paper by Support vector machine (SVM) can achieve 100% recognition accuracy. By enabling faster and more accurate leak detection, the method minimizes gas loss, as well as mitigating the environmental risks caused by this potent greenhouse gas.
暂无评论